Papers › Hierarchical Temporal Convolution Network:Towards Privacy-Centric Activity Recognition

Hierarchical Temporal Convolution Network:Towards Privacy-Centric Activity Recognition

21 Dec 2024International Conference on Ubiquitous Computing and Ambient Intelligence 2024 12archive 2025-07-28

Vincent Gbouna Zakka, Zhuangzhuang Dai, Luis J. Manso

In response to the healthcare issues associated with the ageing population, various ambient assisted living technologies are being developed. To mitigate privacy concerns related to cloud-based data processing, recent methods have shifted towards using edge devices for local data processing. Despite their perceived benefits, the limited computational resources of these edge devices present a significant challenge for real-time performance, which is often an imperative requirement. However, recent computer vision-based methods for recognising activities of daily living among the elderly face increased computational complexity when capturing the multi-scale temporal context essential for accurate activity recognition. In this context, we propose HT-ConvNet (Hierarchical Temporal Convolution Network) to capture multi-scale temporal information without increasing computational complexity. HT-ConvNet employs exponentially increasing receptive fields across successive convolution layers to enable efficient hierarchical extraction of temporal features. Furthermore, HT-ConvNet provides an adaptive weighting mechanism to emphasise the most important features. Experimental results show that the multi-scale temporal feature extraction and the feature-weighted fusion mechanisms outperform existing methods in enhancing accuracy without increasing model complexity. The code is publicly available in: https://github.com/Gbouna/HT-ConvNet.

PaperPDFCode

Code

Gbouna/HT-ConvNet mentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Activity RecognitionSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition J-HMDB HT-ConvNet Accuracy (RGB+pose) - #11 of 13 Archive leaderboard report
Skeleton Based Action Recognition J-HMDB HT-ConvNet Accuracy (pose) 86.1 #11 of 13 Archive leaderboard report
Skeleton Based Action Recognition JHMDB (2D poses only) HT-ConvNet Accuracy 86.1 #1 of 6 Archive leaderboard report
Skeleton Based Action Recognition JHMDB (2D poses only) HT-ConvNet Average accuracy of 3 splits 86.1 #1 of 6 Archive leaderboard report
Skeleton Based Action Recognition JHMDB (2D poses only) HT-ConvNet No. parameters 1.75 #1 of 6 Archive leaderboard report
Skeleton Based Action Recognition SHREC 2017 track on 3D Hand Gesture Recognition HT-ConvNet 14 gestures accuracy 97.1 #4 of 7 Archive leaderboard report
Skeleton Based Action Recognition SHREC 2017 track on 3D Hand Gesture Recognition HT-ConvNet 28 gestures accuracy 94.3 #4 of 7 Archive leaderboard report
Skeleton Based Action Recognition SHREC 2017 track on 3D Hand Gesture Recognition HT-ConvNet No. Parameters 1.75 #4 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections